Elizabeth Olsen Sdxl Flux
模型简介
该模型通过LoRA微调技术,可在稳定扩散框架下生成以伊丽莎白·奥尔森为原型的各类肖像,包括证件照、艺术肖像及漫威角色扮演等场景,支持高度细节化的特征控制
模型特点
名人特征精准还原
特别优化了伊丽莎白·奥尔森的面部特征和漫威猩红女巫造型的细节表现
多场景适配
支持从正式证件照到奇幻角色扮演的多样化图像生成需求
FLUX.1-dev优化
基于black-forest-labs/FLUX.1-dev基础模型,增强照片级真实感表现
细粒度控制
通过详细文本描述可精确控制服饰、配饰、表情等视觉元素
模型能力
高质量肖像生成
角色扮演图像合成
多风格图像转换
细节特征控制
使用案例
证件照生成
专业护照照片
生成符合要求的正式证件照,可自定义发型、服饰和配饰
32784958.jpeg等示例展示
艺术创作
漫威角色扮演
生成猩红女巫主题的奇幻肖像,包含混沌魔法特效等元素
example_w6n0petr4.png等示例展示
历史场景再现
将人物置于古罗马等历史场景中,生成符合时代特征的肖像
32702487.jpeg示例展示
商业应用
宣传素材生成
快速生成带有特定文字或品牌元素的宣传图片
32702761.jpeg示例展示
🚀 Elizabeth Olsen (SDXL+FLUX)
这是一个基于文本到图像生成的模型,能够生成以Elizabeth Olsen为主题的高质量图像,尤其在生成Marvel Comics中Scarlet Witch形象时表现出色。
🚀 快速开始
模型下载
此模型的权重以Safetensors格式提供。你可以在 Files & versions 标签页 中下载。
使用🧨 diffusers库
from diffusers import AutoPipelineForText2Image
import torch
device = "cuda" if torch.cuda.is_available() else "cpu"
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('Keltezaa/elizabeth-olsen-sdxl-flux', weight_name='eliolsen_2017_local_164_merger_20v1_8v2_34v2_03_03_04.safetensors')
image = pipeline('High quality passport photo of a woman with wavy blonde hair wearing a suit and tie looking directly at the camera with her mouth closed and a neutral expression. She is also wearing a delicate gold chain and some understated diamond earrings.').images[0]
如需了解更多细节,包括LoRAs的加权、合并和融合,请查看 diffusers中加载LoRAs的文档。
💻 使用示例
基础用法
from diffusers import AutoPipelineForText2Image
import torch
device = "cuda" if torch.cuda.is_available() else "cpu"
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('Keltezaa/elizabeth-olsen-sdxl-flux', weight_name='eliolsen_2017_local_164_merger_20v1_8v2_34v2_03_03_04.safetensors')
image = pipeline('High quality passport photo of a woman with wavy blonde hair wearing a suit and tie looking directly at the camera with her mouth closed and a neutral expression. She is also wearing a delicate gold chain and some understated diamond earrings.').images[0]
高级用法
# 这里可以根据具体的高级使用场景进行代码编写和说明
# 例如,调整参数、使用不同的提示词等
# 以下是一个简单示例,假设可以调整生成图像的尺寸
from diffusers import AutoPipelineForText2Image
import torch
device = "cuda" if torch.cuda.is_available() else "cpu"
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('Keltezaa/elizabeth-olsen-sdxl-flux', weight_name='eliolsen_2017_local_164_merger_20v1_8v2_34v2_03_03_04.safetensors')
prompt = 'High quality passport photo of a woman with wavy blonde hair wearing a suit and tie looking directly at the camera with her mouth closed and a neutral expression. She is also wearing a delicate gold chain and some understated diamond earrings.'
image = pipeline(prompt, width=800, height=800).images[0]
📄 许可证
本模型使用的许可证为 bespoke-lora-trained-license。
模型信息
属性 | 详情 |
---|---|
模型类型 | 文本到图像生成模型,基于Stable Diffusion和LoRA技术 |
基础模型 | black-forest-labs/FLUX.1-dev |
标签 | text-to-image, stable-diffusion, lora, diffusers, template:sd-lora, migrated, photorealistic, marvel, woman, celebrity |
示例输出
提示文本 | 输出图像链接 |
---|---|
High quality passport photo of a woman wearing a suit and tie looking directly at the camera with her mouth closed and a neutral expression. She is also wearing a delicate gold chain and some understated diamond earrings. | 32784958.jpeg |
A closeup portrait photo of a woman with medium length hair who gazing directly at the camera with a neutral expression. She is wearing a multicolored knitted sweater against a dark background. Spotlight illumination. | 32702445.jpeg |
Instagram selfie of a woman during the ancient roman empire standing in the middle of a marketplace in ancient rome with people and merchants all around her. She has a toga on as would be befitting for a madam of the house and has a neutral expression. She has almost no makeup on. Her hair is in an intricate updo and held together by some golden hairpins. | 32702487.jpeg |
High res waist up portrait photo of a woman with her hair in platinum blonde box-braids with glittery eye-shadow and clear glossy lip-gloss. She is looking at the viewer with her mouth closed. She is wearing a thin string-like black choker and hoop earrings. In the background is a nightclub scene out of focus. | 32704240.jpeg |
Instagram photo of a woman sitting at a table wearing a light grey sweatshirt with green polka-dots on it, holding a sign that has the writing "Welcome to FLUX!!" written on it. She is looking at the camera with a slight smile and in the background are some office plants on either side of her out of focus. | 32702761.jpeg |
High quality passport photo of a woman with long wavy golden-blonde hair wearing a suit and tie looking directly at the camera with her mouth closed and a neutral expression. She is also wearing a delicate gold chain. | 32705182.jpeg |
High quality photo in side view of a woman looking at the viewer standing on top of a hill in the windy scottish highlands wearing a tight full sleeve figure hugging turtle neck shirt and white dress pants that are also form fitted. | 32702970.jpeg |
Instagram photo of a blonde woman with freckles on her face in the winter outdoors silhouette illumination of her hair. Taken with a ProPhoto iPhone camera. | 32703037.jpeg |
Contact sheet with 4 images of a woman with a messy short bob cut wearing a black turtleneck. | 32702875.jpeg |
High quality passport photo of a woman with wavy blonde hair wearing a suit and tie looking directly at the camera with her mouth closed and a neutral expression. She is also wearing a delicate gold chain and some understated diamond earrings. | 32785711.jpeg |
(Elizabeth Olsen:1.2)A captivating portrait of Marvel Comics' Scarlet Witch, Wanda Maximoff, with an ethereal quality that reflects her chaotic and powerful abilities. She stands in the center, her crimson hair cascading down in soft waves that frame her delicate yet intense expression. Her eyes are a piercing shade of emerald, hinting at the untamed mystical forces within her. She wears her iconic costume, consisting of a form-fitting red dress with a plunging neckline and gold accents that trace the lines of her body, emphasizing her voluptuous figure. The dress transitions into a flowing skirt that flares out slightly at her hips, giving her an aura of elegance and danger. The crimson hue of the dress matches her skin-tight leather boots that reach up to her thighs, adorned with golden laces and buckles. On her left hand, she wears the crimson gauntlet that channels her power, while her right hand is raised, her fingers curling as if casting a spell. Swirling around her wrist and forearm are intricate patterns of glowing red energy, a visual representation of her chaos magic. The background is a blend of dark purples and smoky blues, with flickering lights and spectral shapes hinting at the turbulent dimension of the Hex. Her left eye is slightly obscured by a lock of hair that's been pushed aside by an invisible force, revealing a sliver of her true power. The overall composition is dynamic and enigmatic, with a focus on the interplay of light and shadow that enhances the mystical and haunting atmosphere of the piece. | images/example_w6n0petr4.png |
(Elizabeth Olsen:1.2)A captivating passport photo of Marvel Comics' Scarlet Witch, Wanda Maximoff, with an ethereal quality that reflects her chaotic and powerful abilities. her crimson hair cascading down in soft waves with intricate patterns of glowing red energy that frame her delicate yet intense expression. She wears her iconic costume, consisting of a form-fitting red dress with a plunging neckline and gold accents that trace the lines of her body, emphasizing her voluptuous figure. On her left hand, she wears the crimson gauntlet that channels her power, while her right hand is raised, her fingers curling as if casting a spell. Swirling around her wrist and forearm are intricate patterns of glowing red energy, a visual representation of her chaos magic. The background is a blend of dark purples and smoky blues, with flickering lights and spectral shapes hinting at the turbulent dimension of the Hex. Her left eye is slightly obscured by a lock of hair that's been pushed aside by an invisible force, revealing a sliver of her true power. The overall composition is dynamic and enigmatic, with a focus on the interplay of light and shadow that enhances the mystical and haunting atmosphere of the piece. | images/example_346c9qxz5.png |
(Elizabeth Olsen:1.2)A captivating passport photo of Marvel Comics' Scarlet Witch, Wanda Maximoff, with an ethereal quality that reflects her chaotic and powerful abilities. her crimson hair cascading down in soft waves with intricate patterns of glowing red flaming energy that frame her delicate yet intense expression. She wears her iconic costume, consisting of a her iconic gold headband with a ruby red gem as a center piece and form-fitting red dress with a plunging neckline and gold accents that trace the lines of her body, emphasizing her voluptuous figure. On her left hand, she wears the crimson gauntlet that channels her power, while her right hand is raised, her fingers curling as if casting a spell. Swirling around her wrist and forearm are intricate patterns of glowing red energy, a visual representation of her chaos magic. The background is a blend of dark purples and smoky blues, with flickering lights and spectral shapes hinting at the turbulent dimension of the Hex. Her left eye is slightly obscured by a lock of hair that's been pushed aside by an invisible force, revealing a sliver of her true power. The overall composition is dynamic and enigmatic, with a focus on the interplay of light and shadow that enhances the mystical and haunting atmosphere of the piece. | images/example_emdmjecis.png |
Clip Vit Large Patch14 336
基于Vision Transformer架构的大规模视觉语言预训练模型,支持图像与文本的跨模态理解
文本生成图像
Transformers

C
openai
5.9M
241
Fashion Clip
MIT
FashionCLIP是基于CLIP开发的视觉语言模型,专门针对时尚领域进行微调,能够生成通用产品表征。
文本生成图像
Transformers 英语

F
patrickjohncyh
3.8M
222
Gemma 3 1b It
Gemma 3是Google推出的轻量级先进开放模型系列,基于与Gemini模型相同的研究和技术构建。该模型是多模态模型,能够处理文本和图像输入并生成文本输出。
文本生成图像
Transformers

G
google
2.1M
347
Blip Vqa Base
Bsd-3-clause
BLIP是一个统一的视觉语言预训练框架,擅长视觉问答任务,通过语言-图像联合训练实现多模态理解与生成能力
文本生成图像
Transformers

B
Salesforce
1.9M
154
CLIP ViT H 14 Laion2b S32b B79k
MIT
基于OpenCLIP框架在LAION-2B英文数据集上训练的视觉-语言模型,支持零样本图像分类和跨模态检索任务
文本生成图像
Safetensors
C
laion
1.8M
368
CLIP ViT B 32 Laion2b S34b B79k
MIT
基于OpenCLIP框架在LAION-2B英语子集上训练的视觉-语言模型,支持零样本图像分类和跨模态检索
文本生成图像
Safetensors
C
laion
1.1M
112
Pickscore V1
PickScore v1 是一个针对文本生成图像的评分函数,可用于预测人类偏好、评估模型性能和图像排序等任务。
文本生成图像
Transformers

P
yuvalkirstain
1.1M
44
Owlv2 Base Patch16 Ensemble
Apache-2.0
OWLv2是一种零样本文本条件目标检测模型,可通过文本查询在图像中定位对象。
文本生成图像
Transformers

O
google
932.80k
99
Llama 3.2 11B Vision Instruct
Llama 3.2 是 Meta 发布的多语言多模态大型语言模型,支持图像文本到文本的转换任务,具备强大的跨模态理解能力。
文本生成图像
Transformers 支持多种语言

L
meta-llama
784.19k
1,424
Owlvit Base Patch32
Apache-2.0
OWL-ViT是一个零样本文本条件目标检测模型,可以通过文本查询搜索图像中的对象,无需特定类别的训练数据。
文本生成图像
Transformers

O
google
764.95k
129
精选推荐AI模型
Llama 3 Typhoon V1.5x 8b Instruct
专为泰语设计的80亿参数指令模型,性能媲美GPT-3.5-turbo,优化了应用场景、检索增强生成、受限生成和推理任务
大型语言模型
Transformers 支持多种语言

L
scb10x
3,269
16
Cadet Tiny
Openrail
Cadet-Tiny是一个基于SODA数据集训练的超小型对话模型,专为边缘设备推理设计,体积仅为Cosmo-3B模型的2%左右。
对话系统
Transformers 英语

C
ToddGoldfarb
2,691
6
Roberta Base Chinese Extractive Qa
基于RoBERTa架构的中文抽取式问答模型,适用于从给定文本中提取答案的任务。
问答系统 中文
R
uer
2,694
98